Results for litellm-client

Production-grade TypeScript client for the LiteLLM proxy server. Zero runtime dependencies, full surface coverage, streaming, retries, typed errors.

LiteLLM client and configuration helpers for ModelDock.

n8n community node for OpenAI with LiteLLM prompt caching support

Xyne CLI - A powerful AI assistant in your terminal with file operations, bash mode, drag-and-drop support, and multi-provider AI integration

JS Implementation of LiteLLM

Token usage in, dollar totals out.

LiteLLM proxy provider extension for Pi

See where your AI coding tokens go - by task, tool, model, and project

Typescript client for the Hugging Face Inference Providers and Inference Endpoints

OpenCode plugin for LiteLLM proxy support with auto-detection and dynamic model discovery

LiteLLM auto-generated type-safe API client

OpenCode plugin that displays which model was selected by a LiteLLM auto router (complexity router, semantic router, etc.)

Get the metadata from a Google Cloud Platform environment

Type-safe TypeScript SDK for LiteLLM.

Google APIs Authentication Client Library for Node.js

OpenCode plugin for any LiteLLM proxy — auto-discovers models, auth, and capabilities

A result paging utility used by Google node.js modules

Custom n8n node to connect with LiteLLM embeddings API

Simple to use, blazing fast and thoroughly tested websocket client and server for Node.js

Production-grade unified multimodal LLM client for the Tamasha LiteLLM proxy. Supports GPT and Gemini families through a single API surface with adapter, transformer, and strategy patterns.

A simple utility for promisifying functions and classes.

OpenAI-compatible proxy for Cursor CLI — use Cursor models from any LLM client on localhost

GOV.UK Notify Node.js client

A simple utility for replacing the projectid token in objects.